Semantic caching reduces LLM inference costs by returning cached responses for semantically similar queries, but current evaluation using PR‑AUC only ranks scores and ignores usability at a fixed threshold, leading to poor deployment choices. The authors propose a cache‑aware metric, Precision–Cache Hit Ratio (P‑CHR) AUC, and an Operational Retention Rate (ORR) to measure how offline ranking quality translates to deployment. They decompose the operational gap into a recoverable threshold‑utility component and an irreducible structural component, showing that the gap is driven by the training objective rather than data scale and can be mitigated by score re‑normalization or objective changes, framing model selection as a threshold‑utility problem.
By Aditeya Baral, Radoslav Ralev, Iliya Sotirov Zhechev, Srijith Rajamohan, Jen Agarwal
arXiv:2607. 04281v1 Announce Type: cross Abstract: Semantic caching reduces the latency and cost of retrieval-augmented generation (RAG) by serving cached answers to semantically similar queries, but most existing methods do not model the time-varying freshness of open-web evidence.
By Muhammad Mansoor, Tahir Ahmad, Yeo-Chan Yoon
arXiv:2607. 20507v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for program-aided reasoning, agentic decision making, and structured task execution, but these applications often incur high inference cost.
By Jingquan Chen, Jinghua Piao, Jie Feng, Shaogang Hu, Yong Li
arXiv:2605. 07096v2 Announce Type: replace Abstract: Evaluating a new model on an existing benchmark is often necessary to understand its behavior before deployment.
By Hayden Helm, Ben Johnson, Carey Priebe
arXiv:2607. 15516v1 Announce Type: cross Abstract: Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent).
By Yan Song
arXiv:2609.36722v1 Announce Type: new
Abstract: Large language model (LLM) agents repeatedly load reusable content, such as skills, documents, and memory entries, into the current context. Re-encodin...
By Xinghao Chen, Junnan Dong, Cai Ke, Chak Tou Leong, Haocheng Sun, Keyu Chen, Siyu An, Ruizhi Qiao, Xing Sun, Wenjie Li, Xiaoyu Shen
The paper introduces SCX Router, a lightweight GLiClass-based model selector that assigns suitability scores to inference-time language models without autoregressive generation. It uses a 0.6B-parameter Qwen3 decoder with a shallow bidirectional scorer, preserving a text-only key–value cache across sessions and predicting task attributes such as type, difficulty, and expected output length. The authors build a comprehensive task ontology with 23 families, 115 types, and 1,173 synthetic examples, generating 150,000 verifier-scored tasks to train the router, which outperforms baseline models on LiveBench subsets with a top‑1 score of 0.707 versus 0.696 for the strongest fixed model.
By Ihor Stepanov, Aleksandr Smechov, Mykhailo Shtopko, Dmytro Vodianytskyi, Oleksandr Lukashov
CacheSpec is an inference optimization framework that transforms Program-of-Thoughts (PoT) style programs into reusable cache objects for large language models. By employing a small model for semantic variable extraction on cache hits and speculative drafting during target-LLM generation, CacheSpec reduces inference latency and improves cache reuse. Experiments on shopping, web, formula, and code QA datasets demonstrate up to 3.1× speedup in latency and 2.8× throughput gains over traditional PoT methods, while maintaining or improving task quality.
By Jingquan Chen, Jie Feng, Jinghua Piao, Shaogang Hu, Yong Li
arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.
By Zhikang Xie, Xichen Ye, Yifan Wu, Haoshen Yu, Li chenan, Peizhu Gong, Weizhong Zhang, Cheng Jin
arXiv:2606. 07684v1 Announce Type: cross Abstract: Disaggregated serving alleviates memory bottlenecks in Large Language Model (LLM) inference but creates a severe communication bottleneck: transmitting high-dimensional Key-Value (KV) caches often dominates time-to-first-token (TTFT).
By Qianli Ma, Zhiqing Tang, Hanshuai Cui, Zhi Yao, Weijia Jia
arXiv:2608.30647v1 Announce Type: cross
Abstract: Language models can answer from precomputed memory, a model's saved reading of a body of material, reused across requests instead of read again at ea...
By Asa Shepard
arXiv:2608. 08684v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by KV cache memory, yet distributing a limited cache budget across layers remains challenging.
By Dongjie Xu, Kai Qian, Julius, Weijie Shi, Yuxuan Sun, Minghua Tang, Fenglei Jin, Hanchi Dong, Jiajie Xu